reelier.com / guides

The guides.

Step-by-step how-tos for recording, replaying, and gating AI agent workflows with Reelier. Every guide is runnable — real commands, verbatim output, no mockups — and links the terms it uses back to the glossary instead of redefining them.

how-to·4 steps·✓ real output

How to snapshot-test a Claude Code workflow

The mental model is one line: the first run writes the snapshot, and every run after diffs against it.

/guides/snapshot-test-claude-code-workflows
how-to·4 steps·✓ real output

How to record MCP tool calls with a wrap proxy

Some agents keep a transcript you can scan after the fact; some don't.

/guides/record-mcp-tool-calls
how-to·4 steps·✓ real output

How to replay an agent workflow at 0 LLM tokens

A recorded agent workflow does not need a model to run again.

/guides/replay-agent-workflow-zero-tokens
how-to·4 steps·✓ real output

How to gate CI on agent drift

A drift gate turns "the agent quietly did something different" into a red build.

/guides/ci-gate-for-agent-drift
how-to·4 steps·✓ real output

Replay an agent skill on every PR with the Reelier GitHub Action

This guide turns a recorded agent skill into a check that replays on every pull request and blocks the merge the moment the tool calls drift — with no model in the loop and 0 tokens per run.

/guides/github-action-agent-replay
how-to·4 steps·✓ real output

Test your MCP server for regressions by replaying a golden run

The mental model is one line: put Reelier in front of your MCP server, record one healthy pass through the tools you ship, and freeze it as a golden run.

/guides/test-mcp-servers
how-to·5 steps·✓ real output

Run a deterministic cron agent by scheduling a recorded replay

A scheduled agent that re-reasons every wake-up pays the model bill on every single tick — the heartbeat tax.

/guides/deterministic-cron-agents
how-to·4 steps·✓ real output

Build an agent audit trail from Reelier run receipts

Every `reelier run` appends one line to `.reelier/runs/<skill>.jsonl`, written by the harness from observed results — not by the model, from memory.

/guides/agent-audit-trail-receipts
how-to·6 steps·✓ real output

Configure BYOK escalation levels: L0, L1, and L2

Reelier's escalation ladder is a spend ceiling you set per run.

/guides/byok-escalation-levels
how-to·4 steps·✓ real output

Compile a skill from an existing session with reelier from-session

You already ran the workflow once — an agent pulled the data, checked the statuses, wrote the report, and you paid the tokens for it.

/guides/from-session-compile
how-to·4 steps·✓ real output

Diff two agent runs with reelier diff (exit 1 on drift)

`reelier diff <skill>` compares the last two runs of a compiled skill and turns any divergence into an exit code: it prints a per-step verdict, says `SAME` and exits 0 when the two runs are identical, and says `DRIFTED` and exits 1 the moment a step's outcome flips, a step is added or removed, or a step needed a different escalation level to pass.

/guides/diff-two-agent-runs
how-to·5 steps·✓ real output

Convert an LLM agent skill into a deterministic, assertion-checked skill

An LLM-executed skill is a `SKILL.md` full of prose: the model reads your instructions and decides the tool calls fresh on every run.

/guides/convert-agent-skill-deterministic
Reading as an agent? Every guide has a raw-markdown twin at /guides/<slug>/md — same data, same renderer, so the two surfaces can't drift. Definitions live in the glossary; the tools these guides compare against are on the comparison pages.